INDEX
Explanations
the string "ser"
New Auto-Interp
Negative Logits
.
-0.95
-0.82
co
-0.82
or
-0.80
in
-0.80
&
-0.79
o
-0.76
of
-0.75
a
-0.74
@
-0.73
POSITIVE LOGITS
itſelf
1.60
auffi
1.57
iſt
1.56
Efq
1.53
myſelf
1.51
Monfieur
1.45
doubtnut
1.42
themſelves
1.40
Majefty
1.40
Jefus
1.38
Activations Density 2.854%